Skip to content
aiqbench

Microsoft · model passport

Phi 3 Mini 4k Instruct June 2024

phi-3-mini-4k-instruct-june-2024
  • Open weights
  • MIT licence
  • Released 2024-06-01(curated)
4/27axes covered
Overall · LMArena
1,143#361 of 396
Best percentile
12.9Hard prompts
Cohort standing
27.7median 34.9

What the data says

Benchmarked on 4 of 27 tracked axes. Every figure below is the model's own published result on that board.

Weakest axes

  • 9.1 pct — Overall (1,143)
  • 10.4 pct — Instruction following (1,124)
  • 11.8 pct — Coding (1,197)

Uneven: 3.8 percentile points between its best and worst axis — 12.9 pct on Hard prompts versus 9.1 pct on Overall.

  • Hard prompts12.9 pct1,176Verify →
  • Coding11.8 pct1,197Verify →
  • Instruction following10.4 pct1,124Verify →
  • Overall9.1 pct1,143Verify →
  • WebDev ArenaNot benchmarked
  • Vision ArenaNot benchmarked
  • Factuality ArenaNot benchmarked
  • Search ArenaNot benchmarked
  • Document ArenaNot benchmarked
  • Agent ArenaNot benchmarked
  • GPQA DiamondNot benchmarked
  • AIME (math)Not benchmarked
  • FrontierMathNot benchmarked
  • SimpleQA VerifiedNot benchmarked
  • ARC-AGI-2Not benchmarked
  • Humanity's Last ExamNot benchmarked
  • SimpleBenchNot benchmarked
  • LiveBenchNot benchmarked
  • BFCL v4 (function calling)Not benchmarked
  • SWE-bench Verified (live board)Not benchmarked
  • Terminal-Bench 4.0Not benchmarked
  • MMLU-Pro (Artificial Analysis)Not benchmarked
  • LiveCodeBench (Artificial Analysis)Not benchmarked
  • IFBench (Artificial Analysis)Not benchmarked
  • HHEM Hallucination (Vectara)Not benchmarked
  • SWE-bench VerifiedNot benchmarked
  • Terminal-BenchNot benchmarked

Percentiles are the model's standing within each board's own population. Axes marked "not benchmarked" have no published result for this model — that is an absence of data, not a low score.

  • phi-3-mini-4k-instruct-june-2024 stands at 27.7 (raw mean 11) — measured on 4 of 27 axes.

    standingtemplateVerify →

  • phi-3-mini-4k-instruct-june-2024 stands at 27.7 versus a cohort median of 34.9 across 123 models released within 180 days — below the peer median.

    cohorttemplateVerify →

Every claim is a computed fact from the current board data, phrased by a low-temperature model call and rejected by a validation gate if any number is not in the source row. How the leaderboards work →